FTS_PRO
Community@fts-pro
FTS_PRO publishes 81 skills spanning agent context engineering, multi-agent architecture, document processing, Chinese social media publishing, and AI image generation.
Agent Skills by FTS_PRO
Showing 80 vetted skills indexed across 1 GitHub repositories.
baoyu-imagine
Generate images via OpenAI, Google, DashScope, Replicate, and other image generation APIs.
planning-with-files
Organizes complex multi-step tasks using persistent markdown planning files on disk.
ui-ux-pro-max
Generates UI/UX design recommendations and searchable guidelines for web and mobile interfaces.
using-git-worktrees
Creates isolated git worktree workspaces with detection, setup, and baseline test verification.
multi-agent-patterns
Design multi-agent architectures using supervisor, swarm, and hierarchical coordination patterns.
defuddle
Extract clean markdown content from web pages using the Defuddle CLI.
bdi-mental-states
Transform RDF context into BDI agent mental states using formal ontology patterns.
baoyu-youtube-transcript
Downloads YouTube transcripts, subtitles, and cover images with caching and chapter segmentation.
baoyu-image-cards
Generates social media infographic image card series with configurable styles, layouts, and palettes.
context-degradation
Diagnose and mitigate context degradation patterns in LLM agent systems.
test-driven-development
Enforces red-green-refactor test-driven development workflow for features and bugfixes.
systematic-debugging
Diagnose bugs through a four-phase root cause investigation process before proposing fixes.
theme-factory
Apply curated color palettes and font pairings to slides, docs, and HTML artifacts.
baoyu-xhs-images
Generates Xiaohongshu image card series with configurable styles, layouts, and color palettes.
context-compression
Implement structured summarization and probe-based evaluation for compressing long agent conversation histories.
baoyu-post-to-weibo
Posts text, images, videos, and Markdown articles to Weibo via Chrome CDP automation.
memory-systems
Designs agent memory architectures using vector stores, knowledge graphs, and temporal retrieval frameworks.
baoyu-infographic
Generate raster infographics by combining 21 layout structures with 22 visual styles.
doc-coauthoring
Guides collaborative document creation through context gathering, iterative drafting, and reader testing.
web-design-guidelines
Review UI code against Vercel Web Interface Guidelines and report findings.
advanced-evaluation
Implement LLM-as-judge evaluation pipelines with bias mitigation and rubric generation.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, and properties.
using-superpowers
Enforces skill discovery and invocation before any AI response or action.
dispatching-parallel-agents
Dispatches concurrent agents to investigate independent test failures across separate problem domains.
Frequently Asked Questions About FTS_PRO
FAQPage SchemaWhat tasks can I accomplish with FTS_PRO's skills?▼
You can engineer agent context (compression, degradation diagnosis, memory systems, BDI mental states), design multi-agent architectures, process PDF/DOCX/XLSX/PPTX files, generate images and infographics, publish to WeChat/Weibo/X, translate documents, and apply React/Next.js/Postgres best practices.
Who is the target audience for these skills?▼
Agent system engineers working on context windows, memory persistence, and multi-agent coordination; content creators targeting Chinese platforms like Xiaohongshu, WeChat, and Weibo; and frontend developers using React, Next.js, React Native, or Obsidian for note management.
What runtime dependencies do the baoyu skills require?▼
Most baoyu-prefixed skills require bun or npx binaries available on the system. baoyu-wechat-summary additionally requires the wx binary (wx-cli), and baoyu-url-to-markdown requires bun with Chrome CDP for site-specific adapters and login handling.
Are FTS_PRO's skills open source?▼
Licensing varies per skill. Vercel-authored skills (react-best-practices, composition-patterns) and supabase-postgres-best-practices are MIT-licensed. Document skills (pdf, docx, xlsx, pptx) are proprietary with terms in LICENSE.txt. Many baoyu skills specify no explicit license.
Which skills help reduce LLM token costs and context limits?▼
Use context-compression for structured summarization, context-optimization for KV-cache and observation masking, filesystem-context for offloading to files, latent-briefing for cross-agent memory without summarization, and context-degradation to diagnose lost-in-middle failures.